© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47152
    Prev
    Next
    INDEX
    Explanations

    explaining why requests violate guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    V
    0.70
    ੀ
    0.61
    T
    0.57
    ة
    0.57
     Haemat
    0.57
    楨
    0.57
    ing
    0.55
    X
    0.54
    िक
    0.53
     paragraph
    0.53
    POSITIVE LOGITS
    n
    0.59
    সিডেন্ট
    0.59
     από
    0.57
     वहाँ
    0.57
     поскольку
    0.55
     พิ
    0.55
     כמו
    0.55
     뽑
    0.55
     которой
    0.54
     ώστε
    0.54
    Activations Density 0.032%

    No Known Activations